Flame Images Research Articles

Advanced image processing techniques for multi-level characterization of significant flame features in carbon-neutral combustion

This research presents an advanced image processing framework designed for the multi-level characterization of significant flame features in carbon-neutral combustion systems. The study introduces an optimized neural network based on a brainstorming algorithm and an enhanced support vector machine (SVM) algorithm, which utilizes an improved particle swarm optimization (PSO) technique. The framework is capable of accurately processing complex flame image data, achieving flame classification accuracy rates of up to 100 %. The proposed system combines detailed analysis of flame brightness, texture, and morphological features, contributing to the comprehensive monitoring of combustion states. Additionally, the paper describes the design of a clean burner that promotes the full combustion of zero-carbon gases. The integration of this burner with the advanced monitoring system significantly enhances safety and efficiency in industrial applications. This work addresses the challenges associated with the transition to renewable gases and provides a robust solution for maintaining stable and efficient combustion processes.

Experimental investigation on ammonia combustion ignited by methanol-enriched active pre-chamber in an optical engine

To enhance the ignitability and burning rate of ammonia-fueled spark ignition engines, it is an effective way to adopt active pre-chamber (PC) ignition with high-reactivity fuel. Therefore, in this paper, the ammonia combustion characteristics using methanol-enriched active PC ignition were investigated, based on optical engine experiments with simultaneous in-cylinder flame imaging and pressure measurement. Results show that the overall combustion process is characterized by a three-stage heat release: (I) jet flame controlled combustion; (II) ammonia flame propagation; (III) post jet induced combustion. In stage I, methanol active PC jets with high-momentum and high-reactivity are discharged to ignite MC ammonia mixture, contributing to the first peak of heat release rate. In stage II, ammonia turbulent flame propagation dominates the combustion. In stage III, post jets induce the third peak of heat release rate. In this way, with a minimal methanol energy ratio (ER) of lower than 10 %, stable and fast ammonia combustion is achieved under stoichiometric (λMC = 1) and lean-burn (λMC = 1.2) condition, with cyclic variation of indicated mean effective pressure (IMEP) lower than 5 %, flame probability higher than 80 % and maximum global flame speed of about 4 m/s. A highest IEMP of 0.72 MPa and a peak indicated thermal efficiency (ηit) of 30 % is obtained at λMC = 1 and λMC = 1.2, respectively. However, at the rich limit of λMC = 0.9 and lean limit of λMC = 1.4, the quenching of jet flames leads to weak ignition and unstable combustion, which is identified by reduced flame probability distribution and increased cyclic variation of IMEP. In addition, to ensure the cyclic combustion stability, there is also an operating range of methanol ER. At λMC = 1.2, unstable ignition and deteriorated combustion occur below the lower limit of ER = 6 % and above the upper limit of ER = 17 %. This paper can provide data support and operation strategy for the combustion improvements of ammonia-methanol active jet ignition engines.

Experimental study on acoustic and flame responses in an annular combustor under azimuthal force

This study investigates the flame dynamics of an annular combustor under various azimuthal acoustic forces. The experimental platform was applied to external azimuthal acoustic force through four loudspeakers installed on the wall outside the plenum. Experiments were conducted with an equivalence ratio of Ф = 0.71 and a combustion power of P = 9.5 kW. Therein, four loudspeakers were used to precisely control the acoustic pressure amplitude, spinning ratio, and spinning direction, which stimulated the first-order standing mode, spinning modes, and second-order standing mode acoustic mode of the plenum, respectively. Our analysis of flame dynamics and acoustic response characteristics was based on different azimuthal modes, combined with dynamic mode decomposition (DMD) of the flame image sequence and acoustic pressure signal. The results corroborate the consistency between the acoustic field quaternion analysis and the flame image sequence DMD results despite varied external forcing conditions. Specifically, the characteristics of the flame vary by the applied forces. Moreover, DMD results indicate that the flame structure of the eigenfrequency mode is asymmetrical in spinning modes and tilts in the direction of the pressure gradient.

Enhancing Accuracy of Flame Equivalence Ratio Measurements: An Attention-Based Convolutional Neural Network Approach for Overcoming Limitations in Traditional Color Modeling.

This paper addresses the inherent limitations in traditional color modeling techniques for measuring the flame equivalence ratio (Φ), particularly focusing on the subjectivity involved in threshold settings and the challenges posed by uneven 2D color distribution. To overcome these issues, this study introduces an attention-based convolutional neural network (ACN) model, a novel approach that transcends the conventional reliance on B/G color features (Tf). The ACN model leverages adaptive feature extraction, augmented by a spatial attention mechanism, to more effectively analyze flame images. By amplifying key features, autonomously minimizing background noise, and standardizing variations in color distribution, the ACN model in this experiment achieved a prediction accuracy of 99%, with a 76% reduction in error rate compared to the original model, significantly improving the accuracy and objectivity of flame Φ measurement. This method marks a substantial development in the precision and reliability of flame analysis.

Investigation of Ammonia/Hydrogen Mixtures and Pilot-Split Strategies in a Laboratory-Scale Radial Swirl Combustor

Abstract The transition to a decarbonized energy future relies on identifying the most suitable alternative fuels that can meet the needs of various energy sectors. While both ammonia and hydrogen are zero-carbon energy vectors, their physical properties and burning characteristics sit on either side of that of natural gas. Hence, mixtures of ammonia and hydrogen are being increasingly looked at as having the potential to fuel current energy systems without requiring significant combustor redesign. However, the combustion characteristics and operation limits for different ammonia/hydrogen mixtures still need to be evaluated. For gas turbine applications in particular, the effect of ammonia/hydrogen mixture composition and operating condition on flame behavior and stability is not well understood. The current work was carried out in a laboratory scale, radial swirl-stabilized turbulent combustor. A systematic study of two ammonia/hydrogen blend ratios (70:30 and 80:20 by volume) and a range of equivalence ratios were tested for different pilot-split ratios, to understand the effect on flame shape, stability and dynamics. Time-resolved pressure and integrated heat release fluctuations were measured to evaluate combustor dynamics, and NH2* chemiluminescence flame images were captured to understand spatial differences in flame structure. When comparing blend ratios, differences were observed in flame macrostructures and combustor dynamics, which could be largely attributed to the considerable difference in the laminar flame speeds of the blends. The addition of pilot generally improved the stability and lean operation for both blend ratios.

Optimised prediction of tunnel fire heat release rate using the ResNet18_2CLSTM model with bagging for multimodal data

Accurate predictions of HRR will improve preparedness and response strategies, enhance safety, and minimise damage in tunnel fires. In this study, a deep learning prediction model for HRR under multimodal data fusion is proposed. A multimodal dataset is first established to obtain flame images and flue gas time series data through model-scale tunnel fire experiments. During the model training process, ResNet18 was used to extract features from the flame image, and 2CLSTM was employed to understand the time series of the flame image features and flue gas features to establish the correlation with the HRR. It was evaluated that the error analyses of the measured and predicted values of the validation set yielded R2 greater than 0.85, with errors and standard deviations less than 4 kW. And the model predicted better in the flame growth and decay phases. However, there is some deviation in the predictions near the peak HRR. To address this issue, the Bagging algorithm was introduced to optimise the model. The results show that the ResNet18_2CLSTM model with Bagging reduces the RMSE by 20.47 % and increases the R2 by 4.64 % compared to the original model, and the accuracy is greatly improved.

Predictive Modeling of NOx Emissions from Lean Direct Injection of Hydrogen and Hydrogen/Natural Gas Blends Using Flame Imaging and Machine Learning

Predictive Modeling of NOx Emissions from Lean Direct Injection of Hydrogen and Hydrogen/Natural Gas Blends Using Flame Imaging and Machine Learning

SDS-YOLOv8n: A lightweight detection method for flames and smoke

Abstract In flame and smoke image processing scenarios, real-time detection of translucent flames and smoke targets is a difficult task. In the process of optimizing accuracy and speed, this study proposed an SDS-YOLOv8n lightweight detection network by using YOLOv8n as a benchmark. First, SimAM was integrated into the SPPF feature pyramid pooling layer to improve the weight attention of the 3D feature map. Secondly, Slim-Neck is used to replace the neck network layer to reduce the parameters and calculations of the model. Finally, the dynamic upsampling operator DySample was used to improve Slim-Neck, integrated into the YOLOv8n lightweight network. Experimental results on the constructed flames and smoke dataset show that the precision rates increased to 81.7%, recall rates increased to 79.2%, and parameters and calculations were reduced by 8% and 18%, respectively. While reducing computing costs, accuracy is improved, and all indicators surpass comparison methods.

Spray combustion characteristics of boron slurry fuel in high particle loading conditions

Enhancing the energy density of hydrocarbon fuels is indeed crucial, especially in the context of addressing energy needs. Incorporating energetic particles as additives into conventional liquid fuels garners increased attention due to its potential to enhance energy density. Due to its high energy potential, boron is the most promising additive in several energetic particles. However, the study focusing on the boron-loaded slurry fuels are limited. Therefore, the present work focuses on the effect of boron loading on the spray combustion of boron-loaded slurry fuel, especially at higher loadings (10%, 20% & 30% boron + Jet A-1 fuel) using a swirl-stabilized spray combustor. The research scrutinizes the feed and exhaust particles' surface morphology, chemical composition and active boron content through diverse particle characterization techniques. Furthermore, the study investigates the influence of boron loading on the combustion characteristics of slurry fuel using methods such as colour flame imaging, spectroscopy, and BO2* Chemiluminescence imaging. The impact of boron loading on the positive thermal contribution of the slurry was examined by analyzing temperature measurements at various locations within the combustor. The BO2* chemiluminescence imaging and spectroscopy results indicate that the intensity of BO2 emission increases with a rise in particle loading. The temperature results reveal an increase in temperature compared to pure Jet A-1 for all the boron-loaded cases. In particular, JB10 and JB20 achieved nearly 90% and 85% of the theoretical temperature increase. The diffractogram and thermogravimetric results of the burnt particles collected show that the particles were burnt thoroughly for the boron-loaded cases.

Passive control of thermoacoustic instability in a high-efficiency domestic gas stove with fine-tuning burner

Thermoacoustic oscillation is a significant challenge in the development of advanced thermal power and propulsion systems. The present work focuses on the whistling phenomenon in the practical burners of a developing high-efficiency domestic gas stove. The acoustic analysis is conducted by a Helmholtz acoustic solver, identifying the 1/2 wave longitudinal mode in the outer ring or center nozzle and its upstream pipe and estimating the modal eigenfrequencies fa=599Hz and fb=647Hz which are close to the main frequency of the whistling measured in experiments. The sequential flame images captured by a high-speed camera are processed by a dynamic mode decomposition method to illustrate flame structure oscillations at the peak frequency mode. The results verify that thermoacoustic oscillations are the generation mechanism of the whistling and display the periodic fluctuation characteristics of the flame and the spatial distribution of heat release. Moreover, both structural fine-tuning designs help to achieve better suppression for thermoacoustic oscillations and avoid the whistling phenomenon. These structural fine-tuning strategies have been researched for several decades but rarely reported to be applied to industrial burners in previous work. Motivated by this, it will provide a new insight into the investigation of burner structures on thermoacoustic behaviors and the application of these passive control strategies.

Prediction of combustion pressure with deep learning using flame images

Deep learning methods provide data-driven techniques for handling large amounts of combustion data, thus finding the hidden patterns underlying these data. This study aims to predict combustion pressure from flame images, which provide more comprehensive information about the combustion process than traditional pressure sensors. The flame images were captured from a single-cylinder 4-stroke optical gasoline direct injection (GDI) engine at 1000 rpm, 5.7 bar IMEP, and stoichiometric combustion conditions using a high-speed camera. To achieve this prediction, we employed five different models: EfficientNetB4, ResNet50, Ensemble Adversarial Inception ResNet, convolutional neural network (CNN), and CNN-XGBoost. The training dataset comprised 1350 flame images captured from a single-cylinder optical GDI engine across different combustion stages. To ensure robustness, 150 images were used for validation. The models were subjected to a testing set of 4500 flame images obtained from different cycles, to evaluate how well they could perform on new, unseen data. The results showed that EfficientNetB4 achieved an impressive R2 of 0.94 and a low RMSE of 0.70 compared to other tested models. Saliency analysis revealed that the model focuses on subtle flame characteristics and areas without intense flames, which suggests that it detects features invisible to the human eye. Additionally, the proposed deep learning approach is applied for the sake of monitoring cycle-to-cycle variations based on in-cylinder flame propagation where it is found that it produces high accuracy compared to those obtained through pressure sensors. Our findings are intended to advance the adoption of machine learning approaches for assisting in engine design and optimization.

Influence of magnetic field on renewable oil flame characteristics-an experimental and image processing analysis with bibliometric study

This study investigates the influence of a magnetic field on the flame characteristics of waste cooking oil. A circular current-carrying coil was used to generate magnetic fields of varying strengths (131.37 G, 234.19 G, 337.07 G, 394.12 G, and 428.39 G), corresponding to different voltages (0–10 V). Flame behavior was captured with a digital camera, both without a magnetic field and under varying field strengths. Flame height and area were analyzed using ImageJ and MATLAB's Image Processing tools. Additionally, the thermal properties and fatty acid composition of the waste cooking oil were examined. Results indicated that the flame height increased by 11.06 % under the strongest magnetic field compared to the baseline. The flame area initially expanded due to magnetically induced diffusion but later decreased as the flame stabilized and turbulence reduced. A strong correlation was found between the flame area estimations from ImageJ and MATLAB.

Effect of operation condition on the venting characteristics of gas/dust two-phase system explosions

This experiment focused on the study of gas and solid two-phase explosions venting characteristics. A comprehensive research of venting parameter, venting flame propagation, temperature distribution, and the influence mechanism of operation condition were revealed. Results indicate that the venting flame experienced the changes of “mushroom”, “spherical” and “strip” structures and was affected by the initial pressure (Pinit) and the film rupture pressure (Pstat). As Pstat≥0.24 MPa, the flame all exhibited a “mushroom” structure and became more prominent as the film rupture pressure increased. The velocity history was increased in the acceleration venting stage as the film rupture pressure and initial pressures enlarged, and flame exhibited an obvious oscillation during extinguishing stage and the average amplitude was also enlarged. As the film rupture pressure further increased, the secondary and third venting processes appeared. The pressure change at the venting port was more significant, even appeared a larger negative pressure and its drop extent continued to increase as the film rupture pressure and initial pressures raised. Tmax appeared in the center of “spherical” flame approach the front end and the extinguished flame still maintained a higher temperature, resulting in a larger distribution outline than the flame image.

Adaptive Control of Ships’ Oil-Fired Boilers Using Flame Image-Based IMC-PID and Deep Reinforcement Learning

The control system of oil-fired boiler units on ships plays a crucial role in reducing the emissions of atmospheric pollutants such as nitrogen oxides (NOx), sulfur dioxides (SO2), and carbon dioxide (CO2). Traditional control methods using conventional measurement sensors face limitations in real-time control due to response delays, which has led to the growing interest in combustion control methods using flame images. To ensure the precision of such combustion control systems, the system model must be thoroughly considered during controller design. However, finding the optimal tuning point is challenging due to the changes in the system model and nonlinearity caused by environmental variations. This study proposes a controller that integrates an internal model control (IMC)-based PID controller with the deep deterministic policy gradient (DDPG) algorithm of deep reinforcement learning to enhance the adaptability of image-based combustion control systems to environmental changes. The proposed controller adjusts the PID parameter values in real-time through the learning of the determination constant lambda (λ) of the IMC internal model. This approach reduces computational resources by shrinking the learning dimensions of the DDPG agent and limits transient responses through constrained learning of control parameters. Experimental results show that the proposed controller exhibited rapid adaptive performance in the learning process for the target oxygen concentration, achieving a reward value of −0.05 within just 105 episodes. Furthermore, when compared to traditional PID tuning methods, the proposed controller demonstrated superior performance, achieving a target value error of 0.0032 and a low overshoot range of 0.0498 to 0.0631, providing the fastest response speed and minimal oscillation. Additionally, experiments conducted on an actual operating ship verified the practical feasibility of this system, highlighting its potential for real-time control and pollutant reduction in marine applications.

Combustion visualization analysis of alternative fuels in the pulverized coal injection raceway through laminar flow reactor

Currently, the steelmaking process uses a pulverized coal injection (PCI) system that serves as the heat source and reductant for ironmaking (blast furnace and FINEX) where system uses expensive high-grade coal and high operating costs. Hydrogen steelmaking is currently being developed to achieve carbon-free operation. To achieve a soft-landing during this phase of rapid change, the use of biomass and inexpensive, thermal coal, and coke dust is necessary. Research on their combustion characteristics is necessary to apply these alternative fuels to PCI. Therefore, this study analyzed the combustion characteristics of ignition delay, devolatilization, and char combustion using a laminar flow reactor visualization equipment that simulates blast furnace (BF) and FINEX PCI tuyere, using flame image data processing. The ignition time were generally longer in BF than in FINEX, and the char combustion length and time also showed the same trend due to the high oxygen rate which indicate under 2 ms on ignition delay, under 16 ms on char combustion. Also, the volatile cloud was qualitatively shown in the image to be highest in thermal coal and biomass with high volatile matter. Based on the correlation and theoretical calculation with proximate analysis and the results, ignition delay time had a combined effect of volatile matter and moisture except coke dust, and char combustion time affected unburned carbon. The combustion chemical characteristics were discussed with chemical percolation devolatilization (CPD) model parameter. Through SEM image and BET analysis, the surface area has been increased more than 10 times after combustion. Consequently, the biomass and high moisture thermal coal could cofired within 10 % and coke dust could be cofired within 9 %, respectively.

До питання про концептипоетичної творчості Володимира Забаштанського

This article outlines the conceptual framework of Volodymyr Zabashtanskyi’s poetic work, particularly focusing on collections such as «Vaha slova (The Weight of the Word)», «Vira v liudynu (Faith in a Man)», «Zhaha zhyttia (Thirst for Life)», «Zapakh dalyny (The Scent of the Farness)», «Moia vuzkokoliika (My Narrow Gauge)», «Naikrevnisha ridnia (The Most Close Relatives)», «Nakaz kameniariv (The Stonemasons’ Order)», «Svichechkoiu slova (By The Candle of the Word)», and «Syni skeli (Blue Rocks)». The study concentrates on the peripheral aspects of Zabashtansky’s poetry, illuminating their ideological and artistic essence. Special attention is given to concepts viewed through solar motifs: the sun, stars, and sky. These motifs are projected onto the intimate world of the lyrical hero, revealing artistic and journalistic intentions and reflections related to the realization of national identity. The concepts of water and land further reinforce these themes, creating a foundation for outlining Zabashtansky’s creative evolution. They depict the essential realities of his small homeland, painting a vivid image of Mother Ukraine. The image-concept of the tree finds its highest embodiment in the concept of the family tree and the archetype of the World Tree, associated with the image of the mother, who brings the new birth of the world and rebirth, protection, and the renewal of the Ukrainian world. Conversely, the concept of flame and related images such as «fire», «blaze», «embers», and others hold significant contextual potential. These images are particularly crucial when transformed into the universal symbols for Ukrainian poetry: the fire of the soul and the fire of the word, which gained prominence at the end of the 19th century. While the industrial perspective is generally not characteristic of Zabashtanskyi’s artistic world, it sporadically appears in the 1980s. This is especially evident in the image-concept of metal, where its ideological and artistic role manifests in the motif of strength — physical, psycho-emotional, and creative. This motif serves as a critical factor in shaping the author’s figure against the backdrop of his era.

Combustion Control of Ship’s Oil-Fired Boilers Based on Prediction of Flame Images

This study proposes and validates a novel combustion control system for oil-fired boilers aimed at reducing air pollutant emissions through flame image prediction. The proposed system is easily applicable to existing ships. Traditional proportional combustion control systems supply fuel and air at fixed ratios according to the set steam load, without considering the emission of air pollutants. To address this, a stable and immediate control system is proposed, which adjusts the air supply to modify the combustion state. The combustion control system utilizes oxygen concentration predictions from flame images via SEF+SVM as control inputs and applies internal model control (IMC)-based proportional-integral (PI) control for real-time combustion control. Due to the complexity of modeling the image-based system, IMC filter constant tuning through experimentation is essential for achieving effective control performance. Experimental results showed that optimal control performance was achieved when the filter constant λ was set to 1.5. In this scenario, the peak overshoot Mp was reduced to 0.19245, and the Integral of Squared Error (ISE) was minimized to 10.1159, ensuring a stable response with minimal oscillation and maintaining a fast response speed. The results demonstrate the potential of the proposed system to improve combustion efficiency and reduce emissions of air pollutants. This study provides a feasible and effective solution for enhancing the environmental performance of marine oil-fired boilers. Given its ease of application to existing ships, it is expected to contribute to sustainable air pollution reduction across the maritime environment.

A full-scale experimental investigation of natural gas explosion in a 710-m long utility tunnel with multiple pipelines

Natural gas poses significant risks to the safe operation of utility tunnels, which house multiple critical infrastructure systems, including natural gas pipelines. To date, no full-scale gas explosion tests in utility tunnels have been published, and there is ongoing debate about whether pipelines can withstand such explosions. This study presents the first-ever 1:1-scale experiments conducted in a 710-meter-long tunnel with cross-sectional dimensions of 3.2 m × 2.6 m. Three pipelines, each approximately 25 m in length and constructed to industrial standards, were used to investigate potential damage. The experiments comprehensively captured the development of flow fields, including flame images, flame signals, temperature, and overpressure, as well as pipeline responses. Results revealed that variations in overpressure within the combustion region were driven by both positive and negative feedback loops. A significant pressure drop was also observed as airflow passed through a local expansion. The experiments further demonstrated that while pipelines within utility tunnels are unlikely to be directly damaged by gas explosions, accessories such as racks are at high risk of severe destruction. These findings offer essential insights for improving the safety design, construct, and operation of tunnel-like spaces involving flammable gases.

Learning-Based Super-Resolution Imaging of Turbulent Flames in Both Time and 3D Space Using Double GAN Architectures

This article presents a spatiotemporal super-resolution (SR) reconstruction model for two common flame types, a swirling and then a jet flame, using double generative adversarial network (GAN) architectures. The approach develops two sets of generator and discriminator networks to learn topographic and temporal features and infer high spatiotemporal resolution turbulent flame structure from supplied low-resolution counterparts at two time points. In this work, numerically simulated 3D turbulent swirling and jet flame structures were used as training data to update the model parameters of the GAN networks. The effectiveness of our model was then thoroughly evaluated in comparison to other traditional interpolation methods. An upscaling factor of 2 in space, which corresponded to an 8-fold increase in the total voxel number and a double time frame acceleration, was used to verify the model’s ability on a swirling flame. The results demonstrate that the assessment metrics, peak signal-to-noise ratio (PSNR), overall error (ER), and structural similarity index (SSIM), with average values of 35.27 dB, 1.7%, and 0.985, respectively, in the spatiotemporal SR results, can reach acceptable accuracy. As a second verification to highlight the present model’s potential universal applicability to flame data of diverse types and shapes, we applied the model to a turbulent jet flame and had equal success. This work provides a different method for acquiring high-resolution 3D structure and further boosting repeat rate, demonstrating the potential of deep learning technology for combustion diagnosis.

Exploration of TKX-50-M (M=Pb, Bi and Cu) as insensitive high-energy combustion catalysts of HMX-CMDB propellant

In order to deal with the long-standing contradiction between safety and performance for propellent combustion catalyst, the TKX-50-M (M=Pb, Bi and Cu) were designed, synthesized and characterized. The density, thermal decomposition, mechanical sensitivity and energy performance of the prepared TKX-50-M were studied systemically. By taking NTO-Pb as the benchmark, the TKX-50-M exhibited much better energetic and safety properties. Besides, the combination of TKX-50-Pb, TKX-50-Cu and carbon black is conductive to the combustion of HMX-CMDB propellant. The burning rate of HMX-CMDB propellant increases from 16.80 to 21.28 mm s−1 at 20 MPa, and the pressure index reduces from 0.87 to 0.39 in the pressure range of 10–20 MPa. The catalytic mechanism of TKX-50-M were explored according to the results of combustion wave structure, flame image and characteristics of burning out surface. The catalytic effect of TKX-50-Pb is mainly reflected in the gas phase region, and the introduction of TKX-50-Cu and carbon black shows a significant synergistic catalytic effect. The results of this study not only help to explore insensitive high-energy combustion catalyst, but also helps to improve the combustion, energy and safety performance of CMDB propellants.